© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10890
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to inequalities or bounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.90
     -
    -0.80
    т
    -0.79
    𝒈
    -0.76
    ли
    -0.74
     Ing
    -0.71
    bigr
    -0.70
    1
    -0.68
    ക്
    -0.68
     "
    -0.66
    POSITIVE LOGITS
    -\
    1.35
     pleaſure
    1.24
     uſed
    1.21
     myſelf
    1.19
     avoient
    1.18
     Jefus
    1.16
    })+\
    1.15
    .}~\
    1.14
    =\
    1.13
     purpoſe
    1.12
    Activations Density 0.305%

    No Known Activations